© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6763
    Prev
    Next
    INDEX
    Explanations

    mixed and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİĢ
    -0.10
    è±ī
    -0.09
    馥
    -0.09
    iest
    -0.09
    æİĢèµ·
    -0.09
    æľīæķĪæĢ§
    -0.08
    åĸ
    -0.08
    å½Ĵå±ŀäºİ
    -0.08
    åĨĴçĿĢ
    -0.08
     havoc
    -0.08
    POSITIVE LOGITS
    æ··åIJĪ
    0.15
    æĹ¢æľī
    0.12
    ä¸Ģéĥ¨åĪĨ
    0.12
    mixed
    0.12
    äºĴè¡¥
    0.11
     mixed
    0.11
    缸ç»ĵåIJĪ
    0.10
    æ··
    0.10
    è¡¥åħħ
    0.10
    åħ¼é¡¾
    0.10
    Activations Density 0.260%

    No Known Activations